Image processing method, apparatus, device and storage medium

1 . An image processing method, comprising:

acquiring an expression image;

adjusting an expression in the expression image based on a preset image processing model to generate a video with a change process of the expression; and

displaying the video,

wherein the image processing model is trained based on expression images of multiple sample objects and multiple videos of changes of expressions of the sample objects, and each of the videos of the changes of the expressions of the sample objects is acquired by migrating a change process of an expression in a preset video to the expression image of the sample object by using a preset migration model and the multiple videos have same expression change features.

2 . The image processing method according to claim 1 , wherein the adjusting an expression in the expression image based on a preset image processing model to generate a video with a change process of the expression comprises:

adjusting at least one of a smile degree or an eye opening or closing degree in the expression image based on the preset image processing model to generate a video with a change process of at least one of the smile degree or the eye opening or closing degree.

3 . The image processing method according to claim 1 , wherein the migration model is trained based on images of a plurality of facial regions and expression differences between the images of the plurality of facial regions, wherein the images of the plurality of facial regions are images of a same type of expression, and expression degrees of the same type of expression in different images are different.

4 . The image processing method according to claim 3 , wherein the images of the plurality of facial regions are extracted based on key points of face in a preset facial image.

5 . A terminal device, comprising:

a memory; and

a processor coupled to the memory, the processor configured to perform an image processing method comprising:

acquiring an expression image;

adjusting an expression in the expression image based on a preset image processing model to generate a video with a change process of the expression; and

displaying the video,

wherein the image processing model is trained based on expression images of multiple sample objects and multiple videos of changes of expressions of the sample objects, and each of the videos of the changes of the expressions of the sample objects is acquired by migrating a change process of an expression in a preset video to the expression image of the sample object by using a preset migration model and the multiple videos have same expression change features.

6 . The terminal device according to claim 5 , wherein the processor is further configured to:

adjust at least one of a smile degree or an eye opening or closing degree in the expression image based on the preset image processing model to generate a video with a change process of at least one of the smile degree or the eye opening or closing degree.

7 . The terminal device according to claim 5 , wherein the migration model is trained based on images of a plurality of facial regions and expression differences between the images of the plurality of facial regions, wherein the images of the plurality of facial regions are images of a same type of expression, and expression degrees of the same type of expression in different images are different.

8 . The terminal device according to claim 7 , wherein the images of the plurality of facial regions are extracted based on key points of face in a preset facial image.

9 . A non-transitory computer-readable storage medium, wherein the storage medium has stored therein a computer program which, when executed by a processor, implements an image processing method comprising:

acquiring an expression image;

adjusting an expression in the expression image based on a preset image processing model to generate a video with a change process of the expression; and

displaying the video,

wherein the image processing model is trained based on expression images of multiple sample objects and multiple videos of changes of expressions of the sample objects, and each of the videos of the changes of the expressions of the sample objects is acquired by migrating a change process of an expression in a preset video to the expression image of the sample object by using a preset migration model and the multiple videos have same expression change features.

10 . The non-transitory computer-readable storage medium according to claim 9 , wherein the image processing method further comprises:

adjusting at least one of a smile degree or an eye opening or closing degree in the expression image based on the preset image processing model to generate a video with a change process of at least one of the smile degree or the eye opening or closing degree.

11 . The non-transitory computer-readable storage medium according to claim 9 , wherein the migration model is trained based on images of a plurality of facial regions and expression differences between the images of the plurality of facial regions, wherein the images of the plurality of facial regions are images of a same type of expression, and expression degrees of the same type of expression in different images are different.

12 . The non-transitory computer-readable storage medium according to claim 11 , wherein the images of the plurality of facial regions are extracted based on key points of face in a preset facial image.